Sampling the Liquid-Gas Critical Point with Boltzmann Generators

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: de Santis, Luigi, Russo, John, Ninarello, Andrea
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918372557455360
author de Santis, Luigi
Russo, John
Ninarello, Andrea
author_facet de Santis, Luigi
Russo, John
Ninarello, Andrea
contents Generative models based on invertible transformations provide a physics-aware route to sample equilibrium configurations directly from the Boltzmann distribution, enabling efficient exploration of complex thermodynamic landscapes. Here, we evaluate their applicability in regions where conventional simulations suffer from severe dynamical bottlenecks, focusing on the liquid-gas critical point of a Lennard-Jones fluid. We show that Boltzmann Generators capture essential signatures of critical behavior, retain reliable performance when trained at or near criticality, and extrapolate across neighboring states of the phase diagram. An intriguing observation is that the model's efficiency metric closely traces the underlying phase boundaries, hinting at a connection between generative performance and thermodynamics. However, the approach remains limited by the small system sizes currently accessible, which suppress the large fluctuations that characterize critical phenomena. Our results delineate the current capabilities and boundaries of Boltzmann Generators in challenging regions of phase space, while pointing toward future applications in problems dominated by slow dynamics, such as glass formation and nucleation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_05109
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Sampling the Liquid-Gas Critical Point with Boltzmann Generators
de Santis, Luigi
Russo, John
Ninarello, Andrea
Statistical Mechanics
Disordered Systems and Neural Networks
Soft Condensed Matter
Generative models based on invertible transformations provide a physics-aware route to sample equilibrium configurations directly from the Boltzmann distribution, enabling efficient exploration of complex thermodynamic landscapes. Here, we evaluate their applicability in regions where conventional simulations suffer from severe dynamical bottlenecks, focusing on the liquid-gas critical point of a Lennard-Jones fluid. We show that Boltzmann Generators capture essential signatures of critical behavior, retain reliable performance when trained at or near criticality, and extrapolate across neighboring states of the phase diagram. An intriguing observation is that the model's efficiency metric closely traces the underlying phase boundaries, hinting at a connection between generative performance and thermodynamics. However, the approach remains limited by the small system sizes currently accessible, which suppress the large fluctuations that characterize critical phenomena. Our results delineate the current capabilities and boundaries of Boltzmann Generators in challenging regions of phase space, while pointing toward future applications in problems dominated by slow dynamics, such as glass formation and nucleation.
title Sampling the Liquid-Gas Critical Point with Boltzmann Generators
topic Statistical Mechanics
Disordered Systems and Neural Networks
Soft Condensed Matter
url https://arxiv.org/abs/2603.05109